ExGate: Externally Controlled Gating for Feature-based Attention in Artificial Neural Networks

The perceptual capabilities of artificial systems have come a long way since the advent of deep learning. These methods have proven to be effective, however, they are not as efficient as their biological counterparts. Visual attention is a set of mechanisms that are employed in biological visual systems to ease the computational load by only processing pertinent parts of the stimuli. This paper addresses the implementation of top-down, feature-based attention in an artificial neural network by the use of externally controlled neuron gating. Our results showed a 5% increase in classification accuracy on the CIFAR-10 dataset versus a non-gated version while adding a limited number of parameters. Our gated model also produces more reasonable errors in predictions by drastically reducing the prediction of classes that belong to a different category than the true class.